Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (9): 2960-2968.DOI: 10.11772/j.issn.1001-9081.2021071343
• Frontier and comprehensive applications • Previous Articles
Yuefeng LIU(), Xiaoyan ZHANG, Wei GUO, Haodong BIAN, Yingjie HE
Received:
2021-07-27
Revised:
2021-10-15
Accepted:
2021-10-21
Online:
2021-10-27
Published:
2022-09-10
Contact:
Yuefeng LIU
About author:
ZHANG Xiaoyan, born in 1997, M. S. candidate. Her research interests include deep learning, prediction of remaining useful life of aero-engine.Supported by:
通讯作者:
刘月峰
作者简介:
张小燕(1997—),女,内蒙古呼和浩特人,硕士研究生,主要研究方向:深度学习、航空发动机剩余寿命预测;基金资助:
CLC Number:
Yuefeng LIU, Xiaoyan ZHANG, Wei GUO, Haodong BIAN, Yingjie HE. Remaining useful life prediction method of aero-engine based on optimized hybrid model[J]. Journal of Computer Applications, 2022, 42(9): 2960-2968.
刘月峰, 张小燕, 郭威, 边浩东, 何滢婕. 基于优化混合模型的航空发动机剩余寿命预测方法[J]. 《计算机应用》唯一官方网站, 2022, 42(9): 2960-2968.
Add to citation manager EndNote|Ris|BibTeX
URL: http://www.joca.cn/EN/10.11772/j.issn.1001-9081.2021071343
数据集 | 运行条件 种类 | 故障模式 种类 | 训练 发动机数 | 测试 发动机数 |
---|---|---|---|---|
FD001 | 1 | 1 | 100 | 100 |
FD002 | 6 | 1 | 260 | 259 |
FD003 | 1 | 2 | 100 | 100 |
FD004 | 6 | 2 | 249 | 248 |
Tab. 1 Description of C-MAPSS datasets
数据集 | 运行条件 种类 | 故障模式 种类 | 训练 发动机数 | 测试 发动机数 |
---|---|---|---|---|
FD001 | 1 | 1 | 100 | 100 |
FD002 | 6 | 1 | 260 | 259 |
FD003 | 1 | 2 | 100 | 100 |
FD004 | 6 | 2 | 249 | 248 |
数据集 | batch size | epoch | winsize | dropout rate | learning rate |
---|---|---|---|---|---|
FD001 | 512 | 20 | 30 | 0.2 | 0.001 |
FD002 | 128 | 30 | 50 | 0.2 | 0.001 |
FD003 | 512 | 20 | 60 | 0.2 | 0.001 |
FD004 | 64 | 20 | 50 | 0.2 | 0.001 |
Tab. 2 Parameter setting
数据集 | batch size | epoch | winsize | dropout rate | learning rate |
---|---|---|---|---|---|
FD001 | 512 | 20 | 30 | 0.2 | 0.001 |
FD002 | 128 | 30 | 50 | 0.2 | 0.001 |
FD003 | 512 | 20 | 60 | 0.2 | 0.001 |
FD004 | 64 | 20 | 50 | 0.2 | 0.001 |
操作 | 选择的传感器 |
---|---|
删除相关性为0% | 2,3,4,6,7,8,9,11,12,13,14,15,17,20,21 |
删除相关性小于30% | 2,3,4,6,7,8,9,11,12,13,15,17,20,21 |
删除相关性小于60% | 2,3,4,7,8,11,12,13,15,17,20,21 |
Tab. 3 Sensor selection results
操作 | 选择的传感器 |
---|---|
删除相关性为0% | 2,3,4,6,7,8,9,11,12,13,14,15,17,20,21 |
删除相关性小于30% | 2,3,4,6,7,8,9,11,12,13,15,17,20,21 |
删除相关性小于60% | 2,3,4,7,8,11,12,13,15,17,20,21 |
数据集 | 删除相关性为0%的传感器 | 删除相关性小于30%的传感器 | 删除相关性小于60%的传感器 | |||
---|---|---|---|---|---|---|
RMSE | Score | RMSE | Score | RMSE | Score | |
FD001 | 13.16 | 259.07 | 13.20 | 259.59 | 13.56 | 292.77 |
FD002 | 16.09 | 1 197.41 | 16.11 | 1 295.10 | 16.26 | 1 340.56 |
FD003 | 13.29 | 304.07 | 13.86 | 345.90 | 13.77 | 309.74 |
FD004 | 17.57 | 1 656.58 | 18.72 | 2 109.16 | 18.55 | 2 080.02 |
Tab. 4 RMSE and Score experimental results with correlation selected sensors
数据集 | 删除相关性为0%的传感器 | 删除相关性小于30%的传感器 | 删除相关性小于60%的传感器 | |||
---|---|---|---|---|---|---|
RMSE | Score | RMSE | Score | RMSE | Score | |
FD001 | 13.16 | 259.07 | 13.20 | 259.59 | 13.56 | 292.77 |
FD002 | 16.09 | 1 197.41 | 16.11 | 1 295.10 | 16.26 | 1 340.56 |
FD003 | 13.29 | 304.07 | 13.86 | 345.90 | 13.77 | 309.74 |
FD004 | 17.57 | 1 656.58 | 18.72 | 2 109.16 | 18.55 | 2 080.02 |
数据集 | 单调性和相关性 | 单调性、可预测性和趋势性 | ||
---|---|---|---|---|
RMSE | Score | RMSE | Score | |
FD001 | 13.56 | 292.77 | 14.30 | 317.89 |
FD002 | 16.26 | 1 340.56 | 16.76 | 1 485.33 |
FD003 | 13.77 | 309.74 | 14.52 | 341.69 |
FD004 | 18.55 | 2 080.02 | 17.99 | 1 850.85 |
Tab. 5 RMSE and Score experimental results of two linear combinations
数据集 | 单调性和相关性 | 单调性、可预测性和趋势性 | ||
---|---|---|---|---|
RMSE | Score | RMSE | Score | |
FD001 | 13.56 | 292.77 | 14.30 | 317.89 |
FD002 | 16.26 | 1 340.56 | 16.76 | 1 485.33 |
FD003 | 13.77 | 309.74 | 14.52 | 341.69 |
FD004 | 18.55 | 2 080.02 | 17.99 | 1 850.85 |
数据集 | 特征提取+全连接网络(Path1) | Bi-LSTM+后置注意力(Path2) | 前置注意力+CNN+Bi-LSTM(Path3) | 本文方法 | ||||
---|---|---|---|---|---|---|---|---|
RMSE | Score | RMSE | Score | RMSE | Score | RMSE | Score | |
FD001 | 14.32 | 308.60 | 13.78 | 255.07 | 13.60 | 234.66 | 12.42 | 224.71 |
FD002 | 15.17 | 1 137.50 | 15.94 | 1 285.67 | 19.01 | 1 709.01 | 15.08 | 1093.10 |
FD003 | 14.78 | 316.05 | 14.36 | 438.68 | 13.84 | 344.51 | 12.64 | 227.24 |
FD004 | 16.45 | 1 610.34 | 16.96 | 1 651.97 | 21.56 | 2 518.23 | 16.10 | 1363.70 |
Tab. 6 RMSE and Score results of ablation experiments
数据集 | 特征提取+全连接网络(Path1) | Bi-LSTM+后置注意力(Path2) | 前置注意力+CNN+Bi-LSTM(Path3) | 本文方法 | ||||
---|---|---|---|---|---|---|---|---|
RMSE | Score | RMSE | Score | RMSE | Score | RMSE | Score | |
FD001 | 14.32 | 308.60 | 13.78 | 255.07 | 13.60 | 234.66 | 12.42 | 224.71 |
FD002 | 15.17 | 1 137.50 | 15.94 | 1 285.67 | 19.01 | 1 709.01 | 15.08 | 1093.10 |
FD003 | 14.78 | 316.05 | 14.36 | 438.68 | 13.84 | 344.51 | 12.64 | 227.24 |
FD004 | 16.45 | 1 610.34 | 16.96 | 1 651.97 | 21.56 | 2 518.23 | 16.10 | 1363.70 |
方法 | 数据集 | |||||||
---|---|---|---|---|---|---|---|---|
FD001 | FD002 | FD003 | FD004 | |||||
Score | RMSE | Score | RMSE | Score | RMSE | Score | RMSE | |
RF[ | 479.95 | 17.910 | 70 456.86 | 29.59 | 711.13 | 20.27 | 46 567.63 | 31.120 |
GB[ | 474.01 | 15.670 | 87 280.06 | 29.09 | 576.72 | 16.84 | 17 817.92 | 29.010 |
LSTM[ | 338.00 | 16.140 | 4 450.00 | 24.49 | 852.00 | 16.18 | 5 550.00 | 28.170 |
BiLSTM[ | 295.00 | 13.650 | 4 130.00 | 23.18 | 317.00 | 12.74 | 5 430.00 | 24.860 |
LSTMBS[ | 481.10 | 14.890 | 7 982.00 | 26.86 | 493.40 | 15.11 | 5 200.00 | 27.110 |
AGCNN[ | 225.51 | 12.420 | 1 492.00 | 19.43 | 227.09 | 13.39 | 3 392.00 | 21.500 |
RBM+LSTM[ | 231.00 | 12.560 | 3 366.00 | 22.73 | 251.00 | 12.10 | 2 840.00 | 22.660 |
HDNN[ | 245.00 | 13.017 | 1 282.42 | 15.24 | 287.72 | 12.22 | 1 527.42 | 18.156 |
本文方法 | 224.71 | 12.420 | 1093.11 | 15.08 | 227.24 | 12.64 | 1363.72 | 16.100 |
Tab. 7 Comparison of Score and RMSE of different methods
方法 | 数据集 | |||||||
---|---|---|---|---|---|---|---|---|
FD001 | FD002 | FD003 | FD004 | |||||
Score | RMSE | Score | RMSE | Score | RMSE | Score | RMSE | |
RF[ | 479.95 | 17.910 | 70 456.86 | 29.59 | 711.13 | 20.27 | 46 567.63 | 31.120 |
GB[ | 474.01 | 15.670 | 87 280.06 | 29.09 | 576.72 | 16.84 | 17 817.92 | 29.010 |
LSTM[ | 338.00 | 16.140 | 4 450.00 | 24.49 | 852.00 | 16.18 | 5 550.00 | 28.170 |
BiLSTM[ | 295.00 | 13.650 | 4 130.00 | 23.18 | 317.00 | 12.74 | 5 430.00 | 24.860 |
LSTMBS[ | 481.10 | 14.890 | 7 982.00 | 26.86 | 493.40 | 15.11 | 5 200.00 | 27.110 |
AGCNN[ | 225.51 | 12.420 | 1 492.00 | 19.43 | 227.09 | 13.39 | 3 392.00 | 21.500 |
RBM+LSTM[ | 231.00 | 12.560 | 3 366.00 | 22.73 | 251.00 | 12.10 | 2 840.00 | 22.660 |
HDNN[ | 245.00 | 13.017 | 1 282.42 | 15.24 | 287.72 | 12.22 | 1 527.42 | 18.156 |
本文方法 | 224.71 | 12.420 | 1093.11 | 15.08 | 227.24 | 12.64 | 1363.72 | 16.100 |
1 | ZHAI Q Q, YE Z S. RUL prediction of deteriorating products using an adaptive wiener process model[J]. IEEE Transactions on Industrial Informatics, 2017, 13(6): 2911-2921. 10.1109/TII.2017.2684821 |
2 | LOUTAS T H, ROULIAS D, GEORGOULAS G. Remaining useful life estimation in rolling bearings utilizing data-driven probabilistic e-support vectors regression[J]. IEEE Transactions on Reliability, 2013, 62(4): 821-832. 10.1109/tr.2013.2285318 |
3 | LIAO L X, KÖTTIG F. Review of hybrid prognostics approaches for remaining useful life prediction of engineered systems, and an application to battery life prediction[J]. IEEE Transactions on Reliability, 2014, 63(1): 191-207. 10.1109/tr.2014.2299152 |
4 | AL-DULAIMI A, ZABIHI S, ASIF A, et al. NBLSTM: noisy and hybrid convolutional neural network and BLSTM-based deep architecture for remaining useful life estimation[J]. Journal of Computing and Information Science in Engineering, 2020, 20(2): No.021012. 10.1115/1.4045491 |
5 | CAI H S, JIA X D, FENG J S, et al. A similarity based methodology for machine prognostics by using kernel two sample test[J]. ISA Transactions, 2020, 103: 112-121. 10.1016/j.isatra.2020.03.007 |
6 | DENG K Y, ZHANG X Y, CHENG Y J, et al. A remaining useful life prediction method with long-short term feature processing for aircraft engines[J]. Applied Soft Computing, 2020, 93: No.106344. 10.1016/j.asoc.2020.106344 |
7 | HOU G S, XU S, ZHOU N, et al. Remaining useful life estimation using deep convolutional generative adversarial networks based on an autoencoder scheme[J]. Computational Intelligence and Neuroscience, 2020, 2020: No.9601389. 10.1155/2020/9601389 |
8 | HUANG C G, HUANG H Z, PENG W W, et al. Improved trajectory similarity-based approach for turbofan engine prognostics[J]. Journal of Mechanical Science and Technology, 2019, 33(10): 4877-4890. 10.1007/s12206-019-0928-3 |
9 | HONG C W, LEE C, LEE K, et al. Remaining useful life prognosis for turbofan engine using explainable deep neural networks with dimensionality reduction[J]. Sensors, 2020, 20(22): No.6626. 10.3390/s20226626 |
10 | HONG C W, LEE K, KO M S, et al. Multivariate time series forecasting for remaining useful life of turbofan engine using deep-stacked neural network and correlation analysis[C]// Proceedings of the 2020 IEEE International Conference on Big Data and Smart Computing. Piscataway: IEEE, 2020: 63-70. 10.1109/bigcomp48618.2020.00-98 |
11 | BEKTAS O, JONES J A, SANKARARAMAN S, et al. A neural network filtering approach for similarity-based remaining useful life estimation[J]. The International Journal of Advanced Manufacturing Technology, 2019, 101(1/2/3/4): 87-103. 10.1007/s00170-018-2874-0 |
12 | WU J, HU K, CHENG Y W, et al. Ensemble recurrent neural network-based residual useful life prognostics of aircraft engines[J]. Structural Durability and Health Monitoring, 2019, 13(3): 317-329. 10.32604/sdhm.2019.05571 |
13 | WU J, HU K, CHENG Y W, et al. Data-driven remaining useful life prediction via multiple sensor signals and deep long short-term memory neural network[J]. ISA Transactions, 2020, 97: 241-250. 10.1016/j.isatra.2019.07.004 |
14 | OMPUSUNGGU A P, PAPY J M, VANDENPLAS S. Kalman-filtering-based prognostics for automatic transmission clutches[J]. IEEE/ASME Transactions on Mechatronics, 2016, 21(1): 419-430. |
15 | JAVED K, GOURIVEAU R, ZERHOUNI N. A new multivariate approach for prognostics based on extreme learning machine and fuzzy clustering[J]. IEEE Transactions on Cybernetics, 2015, 45(12): 2626-2639. 10.1109/tcyb.2014.2378056 |
16 | WU D Z, JENNINGS C, TERPENNY J, et al. A comparative study on machine learning algorithms for smart manufacturing: tool wear prediction using random forests[J]. Journal of Manufacturing Science and Engineering, 2017, 139(7): No.071018. 10.1115/1.4036350 |
17 | WU Y T, YUAN M, DONG S P, et al. Remaining useful life estimation of engineered systems using vanilla LSTM neural networks[J]. Neurocomputing, 2018, 275: 167-179. 10.1016/j.neucom.2017.05.063 |
18 | 李京峰,陈云翔,项华春,等. 基于LSTM-DBN的航空发动机剩余寿命预测[J]. 系统工程与电子技术, 2020, 42(7): 1637-1644. 10.3969/j.issn.1001-506X.2020.07.28 |
LI J F, CHEN Y X, XIANG H C, et al. Remaining useful life prediction for aircraft engine based on LSTM-DBN[J]. Systems Engineering and Electronics, 2020, 42(7): 1637-1644. 10.3969/j.issn.1001-506X.2020.07.28 | |
19 | LI X, DING Q, SUN J Q. Remaining useful life estimation in prognostics using deep convolution neural networks[J]. Reliability Engineering and System Safety, 2018, 172: 1-11. 10.1016/j.ress.2017.11.021 |
20 | LIU H, LIU Z Y, JIA W Q, et al. A novel deep learning-based encoder-decoder model for remaining useful life prediction[C]// Proceedings of the 2019 International Joint Conference on Neural Networks. Piscataway: IEEE, 2019: 1-8. 10.1109/ijcnn.2019.8852129 |
21 | 朱霖,宁芊,雷印杰,等. 基于遗传算法选优的集成手段与时序卷积网络的涡扇发动机剩余寿命预测[J]. 计算机应用, 2020, 40(12): 3534-3540. 10.11772/j.issn.1001-9081.2020050661 |
ZHU L, NING Q, LEI Y J, et al. Remaining useful life prediction for turbofan engines by genetic algorithm-based selective ensembling and temporal convolutional network[J]. Journal of Computer Applications, 2020, 40(12): 3534-3540. 10.11772/j.issn.1001-9081.2020050661 | |
22 | LIU H, LIU Z Y, JIA W Q, et al. Remaining useful life prediction using a novel feature-attention-based end-to-end approach[J]. IEEE Transactions on Industrial Informatics, 2021, 17(2): 1197-1207. 10.1109/tii.2020.2983760 |
23 | JIANG Y L, LI C S, YANG Z X, et al. Remaining useful life estimation combining two-step maximal information coefficient and temporal convolutional network with attention mechanism[J]. IEEE Access, 2021, 9: 16323-16336. 10.1109/access.2021.3052305 |
24 | DAS A, HUSSAIN S, YANG F, et al. Deep recurrent architecture with attention for remaining useful life estimation[C]// Proceedings of the 2019 IEEE Region 10 Conference. Piscataway: IEEE, 2019: 2093-2098. 10.1109/tencon.2019.8929267 |
25 | CHEN Z H, WU M, ZHAO R, et al. Machine remaining useful life prediction via an attention-based deep learning approach[J]. IEEE Transactions on Industrial Electronics, 2021, 68(3): 2521-2531. 10.1109/tie.2020.2972443 |
26 | KHELIF R, CHEBEL-MORELLO B, MALINOWSKI S, et al. Direct remaining useful life estimation based on support vector regression[J]. IEEE Transactions on Industrial Electronics, 2017, 64(3): 2276-2285. 10.1109/tie.2016.2623260 |
27 | ZHANG C, LIM P, QIN A K, et al. Multiobjective deep belief networks ensemble for remaining useful life estimation in prognostics[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(10): 2306-2318. 10.1109/tnnls.2016.2582798 |
28 | ZHENG S, RISTOVSKI K, FARAHAT A, et al. Long short-term memory network for remaining useful life estimation[C]// Proceedings of the 2017 IEEE International Conference on Prognostics and Health Management. Piscataway: IEEE, 2017: 88-95. 10.1109/icphm.2017.7998311 |
29 | WANG J J, WEN G L, YANG S P, et al. Remaining useful life estimation in prognostics using deep bidirectional LSTM neural network[C]// Proceedings of the 2018 Prognostics and System Health Management Conference. Piscataway: IEEE, 2018: 1037-1042. 10.1109/phm-chongqing.2018.00184 |
30 | LIAO Y, ZHANG L X, LIU C D. Uncertainty prediction of remaining useful life using long short-term memory network based on bootstrap method[C]// Proceedings of the 2018 IEEE International Conference on Prognostics and Health Management. Piscataway: IEEE, 2018: 1-8. 10.1109/icphm.2018.8448804 |
31 | ELLEFSEN A L, BJØRLYKHAUG E, ÆSØY V, et al. Remaining useful life predictions for turbofan engine degradation using semi-supervised deep architecture[J]. Reliability Engineering and System Safety, 2019, 183: 240-251. 10.1016/j.ress.2018.11.027 |
32 | AL-DULAIMI A, ZABIHI S, ASIF A, et al. A multimodal and hybrid deep neural network model for remaining useful life estimation[J]. Computers in Industry, 2019, 108: 186-196. 10.1016/j.compind.2019.02.004 |
[1] | Kai WEN, Weiwei TANG, Junchen XIONG. Real-time segmentation algorithm based on attention mechanism and effective factorized convolution [J]. Journal of Computer Applications, 2022, 42(9): 2659-2666. |
[2] | Xudong HOU, Fei TENG, Yi ZHANG. Medical named entity recognition model based on deep auto-encoding [J]. Journal of Computer Applications, 2022, 42(9): 2686-2692. |
[3] | Yaoshun LI, Lizhi LIU. Lightweight network for rebar detection with attention mechanism [J]. Journal of Computer Applications, 2022, 42(9): 2900-2908. |
[4] | Hongjun HENG, Tianbao XU. Attention sentiment analysis model based on multi-scale convolution and gating mechanism [J]. Journal of Computer Applications, 2022, 42(9): 2674-2679. |
[5] | Yuhang WANG, Yongxia ZHOU, Liangwu WU. Pooling algorithm based on Gaussian function [J]. Journal of Computer Applications, 2022, 42(9): 2800-2806. |
[6] | Haiyun WEI, Qianying ZHENG, Jinling YU. Motion blurred image restoration algorithm based on multi-scale network [J]. Journal of Computer Applications, 2022, 42(9): 2838-2844. |
[7] | Wentao ZHANG, Yuanyu WANG, Saize LI. Depth estimation model of single haze image based on conditional generative adversarial network [J]. Journal of Computer Applications, 2022, 42(9): 2865-2875. |
[8] | Minghui WU, Guangjie ZHANG, Canghong JIN. Time series prediction model based on multimodal information fusion [J]. Journal of Computer Applications, 2022, 42(8): 2326-2332. |
[9] | Zhenhu LYU, Xinzheng XU, Fangyan ZHANG. Lightweight attention mechanism module based on squeeze and excitation [J]. Journal of Computer Applications, 2022, 42(8): 2353-2360. |
[10] | Liying ZHANG, Chunjiang PANG, Xinying WANG, Guoliang LI. Multi-scale object detection algorithm based on improved YOLOv3 [J]. Journal of Computer Applications, 2022, 42(8): 2423-2431. |
[11] | Xinyu ZHANG, Sheng DING, Zhipei YANG. Traffic sign detection algorithm based on improved attention mechanism [J]. Journal of Computer Applications, 2022, 42(8): 2378-2385. |
[12] | Yinglü XUAN, Yuan WAN, Jiahui CHEN. Time series classification by LSTM based on multi-scale convolution and attention mechanism [J]. Journal of Computer Applications, 2022, 42(8): 2343-2352. |
[13] | Xianjie ZHANG, Zhiming ZHANG. Handwritten English text recognition based on convolutional neural network and Transformer [J]. Journal of Computer Applications, 2022, 42(8): 2394-2400. |
[14] | Nanjiang CHENG, Zhenxia YU, Lin CHEN, Hezhe QIAO. Multi-source and multi-label pedestrian attribute recognition based on domain adaptation [J]. Journal of Computer Applications, 2022, 42(8): 2401-2406. |
[15] | Kun LI, Qing HOU. Lightweight human pose estimation based on attention mechanism [J]. Journal of Computer Applications, 2022, 42(8): 2407-2414. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||